Link Search Menu Expand Document Documentation Menu

Machine learning

OpenSearch offers two distinct approaches to machine learning (ML): using ML models for tasks like semantic search and text generation, and running statistical algorithms for data analysis. Choose the approach that best fits your use case.

ML models for search and AI/ML-powered applications

OpenSearch supports ML models that you can use to enhance search relevance through semantic understanding. You can either deploy models directly within your OpenSearch cluster or connect to models hosted on external platforms. These models can transform text into vector embeddings, enabling semantic search capabilities, or provide advanced features like text generation and question answering. For more information, see Integrating ML models.

Deploy local models to your cluster

  • Pretrained models: Use OpenSearch-provided models for immediate implementation
  • Custom models: Upload and serve your own models

Connect to externally hosted models

Connect to models hosted on Amazon Bedrock, Amazon SageMaker, OpenAI, Cohere, DeepSeek, and other platforms

OpenSearch Assistant and automation

OpenSearch Assistant Toolkit helps you create AI-powered assistants for OpenSearch Dashboards.

OpenSearch Assistant Toolkit

  • Agents for task orchestration
  • Tools for specific operations
  • Configuration automation

Built-in algorithms for data analysis

OpenSearch includes built-in algorithms that analyze your data directly within your cluster, enabling tasks like anomaly detection, data clustering, and predictive analytics without requiring external ML models.

Supported algorithms

Learn about the natively supported clustering, pattern detection, and statistical analysis algorithms

Build your solution

Get started with AI search

Build your first semantic search application using this hands-on tutorial

AI search

Discover AI search, from semantic, hybrid, and multimodal search to RAG

Tutorials

Follow step-by-step tutorials to integrate AI capabilities into your applications

ML API reference

Explore comprehensive documentation for machine learning API operations

350 characters left

Have a question? .

Want to contribute? or .